KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model

In this paper, we propose KaLM-Embedding-V2, a versatile and compact embedding model, which achieves impressive performance in general-purpose text embedding tasks by leveraging superior training techniques and data. Our key innovations include: (1) To better align the architecture with representation learning, we remove the causal attention mask and adopt a fully bidirectional transformer with simple yet effective mean-pooling to produce fixed-length embeddings; (2) We employ a multi-stage training pipeline: (i) pre-training on large-scale weakly supervised open-source corpora; (ii) fine-tuning on high-quality retrieval and non-retrieval datasets; and (iii) model-soup parameter averaging for robust generalization. Besides, we introduce a focal-style reweighting mechanism that concentrates learning on difficult samples and an online hard-negative mixing strategy to continuously enrich hard negatives without expensive offline mining; (3) We collect over 20 categories of data for pre-training and 100 categories of data for fine-tuning, to boost both the performance and generalization of the embedding model. Extensive evaluations on the Massive Text Embedding Benchmark (MTEB) Chinese and English show that our model significantly outperforms others of comparable size, and competes with 3x, 14x, 18x, and 26x larger embedding models, setting a new standard for a versatile and compact embedding model with less than 1B parameters.

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and constrained viewpoints. On the modeling side, current approaches predominantly rely on supervised fine-tuning, which yields only marginal improvements in reasoning capabilities. To address these challenges, we propose a novel pipeline that constructs a reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images. We introduce GLOBE, Group-relative policy optimization for Locatability assessment and Optimized visual-clue reasoning, yielding Bi-objective geo-Enhancement for the VLM in recognition and reasoning. GLOBE incorporates task-specific rewards that jointly enhance locatability assessment, visual clue reasoning, and geolocation accuracy. Both qualitative and quantitative results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks, particularly in diverse visual scenes, while also generating more insightful and interpretable reasoning trajectories.

Optimizing Singular Spectrum for Large Language Model Compression

Large language models (LLMs) have demonstrated remarkable capabilities, yet prohibitive parameter complexity often hinders their deployment. Existing singular value decomposition (SVD) based compression methods simply deem singular values as importance scores of decomposed components. However, this importance ordered by singular values does not necessarily correlate with the performance of a downstream task. In this work, we introduce SoCo (Singular spectrum optimization for large language model Compression), a novel compression framework that learns to rescale the decomposed components of SVD in a data-driven manner. Concretely, we employ a learnable diagonal matrix to assign importance scores for singular spectrum and develop a three-stage training process that progressively refines these scores from initial coarse compression to fine-grained sparsification-thereby striking an effective balance between aggressive model compression and performance preservation. Thanks to the learnable singular spectrum, SoCo adaptively prunes components according to the sparsified importance scores, rather than relying on the fixed order of singular values. More importantly, the remaining components with amplified importance scores can compensate for the loss of the pruned ones. Experimental evaluations across multiple LLMs and benchmarks demonstrate that SoCo surpasses the state-of-the-art methods in model compression.

Collaborative Diffusion Model for Recommender System

Diffusion-based recommender systems (DR) have gained increasing attention for their advanced generative and denoising capabilities. However, existing DR face two central limitations: (i) a trade-off between enhancing generative capacity via noise injection and retaining the loss of personalized information. (ii) the underutilization of rich item-side information. To address these challenges, we present a Collaborative Diffusion model for Recommender System (CDiff4Rec). Specifically, CDiff4Rec generates pseudo-users from item features and leverages collaborative signals from both real and pseudo personalized neighbors identified through behavioral similarity, thereby effectively reconstructing nuanced user preferences. Experimental results on three public datasets show that CDiff4Rec outperforms competitors by effectively mitigating the loss of personalized information through the integration of item content and collaborative signals.

HiMix: Reducing Computational Complexity in Large Vision-Language Models

Benefiting from recent advancements in large language models and modality alignment techniques, existing Large Vision-Language Models(LVLMs) have achieved prominent performance across a wide range of scenarios. However, the excessive computational complexity limits the widespread use of these models in practical applications. We argue that one main bottleneck in computational complexity is caused by the involvement of redundant vision sequences in model computation. This is inspired by a reassessment of the efficiency of vision and language information transmission in the language decoder of LVLMs. Then, we propose a novel hierarchical vision-language interaction mechanism called Hierarchical Vision injection for Mixture Attention (HiMix). In HiMix, only the language sequence undergoes full forward propagation, while the vision sequence interacts with the language at specific stages within each language decoder layer. It is striking that our approach significantly reduces computational complexity with minimal performance loss. Specifically, HiMix achieves a 10x reduction in the computational cost of the language decoder across multiple LVLM models while maintaining comparable performance. This highlights the advantages of our method, and we hope our research brings new perspectives to the field of vision-language understanding. Project Page: https://xuange923.github.io/HiMix

Manga Generation via Layout-controllable Diffusion

Generating comics through text is widely studied. However, there are few studies on generating multi-panel Manga (Japanese comics) solely based on plain text. Japanese manga contains multiple panels on a single page, with characteristics such as coherence in storytelling, reasonable and diverse page layouts, consistency in characters, and semantic correspondence between panel drawings and panel scripts. Therefore, generating manga poses a significant challenge. This paper presents the manga generation task and constructs the Manga109Story dataset for studying manga generation solely from plain text. Additionally, we propose MangaDiffusion to facilitate the intra-panel and inter-panel information interaction during the manga generation process. The results show that our method particularly ensures the number of panels, reasonable and diverse page layouts. Based on our approach, there is potential to converting a large amount of textual stories into more engaging manga readings, leading to significant application prospects.

Pear: Pruning and Sharing Adapters in Visual Parameter-Efficient Fine-Tuning

Adapters have been widely explored to alleviate computational and storage costs when fine-tuning pretrained foundation models. However, the adapter itself can exhibit redundancy, leading to unnecessary storage overhead and inferior performance. In this paper, we propose Prune and Share (Pear), a novel adapter-pruning framework for efficient fine-tuning of pretrained visual foundation models. Specifically, we prune certain adapters and share the more important unpruned ones with positions where adapters are pruned, allowing continual adaptation at these positions after pruning. Additionally, a knowledge checkpoint strategy is introduced, which preserves the information of the pruned adapters and further boosts performance. Experimental results on visual adaptation benchmark validate the effectiveness and efficiency of the proposed Pear comparing to other competitive methods. Code is in https://github.com/yibozhong/pear.

Low-Rank Interconnected Adaptation Across Layers

Low-rank adaptation (LoRA), as one of the most well-known representative methods of parameter-efficient fine-tuning, freezes the backbone model and introduces parallel adapter modules to each layer of the model. These modules consist of two low-rank trainable matrices: a low-dimension projector (LP) and a high-dimension projector (HP) with their product approximating the change for updating the model weight. However, LoRA's paired LP and HP per layer limit learned weights to specific features, ignoring the varied information extracted by stacked layers in models like Transformers. By considering the differences between layers and establishing connections across them when learning the weights, we enhance the capture of relevant information for downstream tasks using this interconnected adaptation when fine-tuning. Meanwhile, preserving the unique characteristics of each layer and thus selectively mix the learning traits of various layers according to a specific ratio can also be crucial in certain tasks. In this paper, we propose Low-rank Interconnected adaptation across layers (Lily). Specifically, we retain layer-specific LPs (local LPs) for low-dimensional feature projection and unify all HPs into a model-wide global HP, thereby overcoming layer-specific constraints in LoRA. The global HP, layer-independent, supports multiple HP sub-modules, or inspired by Mixture of Experts (MoE), HP experts capturing learning traits across all layer depths. For the ratio to mix all the experts, we use a router inspired by MoE to selectively adapt the features of different layers, thus obtaining a unique expert distribution. We evaluated Lily on a wide range of downstream tasks and achieved state-of-the-art results, outperforming LoRA and a range of competitive methods. Code will be available at https://github.com/blameitonme1/lily.

HEAT: Head-level Parameter Efficient Adaptation of Vision Transformers with Taylor-expansion Importance Scores

Prior computer vision research extensively explores adapting pre-trained vision transformers (ViT) to downstream tasks. However, the substantial number of parameters requiring adaptation has led to a focus on Parameter Efficient Transfer Learning (PETL) as an approach to efficiently adapt large pre-trained models by training only a subset of parameters, achieving both parameter and storage efficiency. Although the significantly reduced parameters have shown promising performance under transfer learning scenarios, the structural redundancy inherent in the model still leaves room for improvement, which warrants further investigation. In this paper, we propose Head-level Efficient Adaptation with Taylor-expansion importance score (HEAT): a simple method that efficiently fine-tuning ViTs at head levels. In particular, the first-order Taylor expansion is employed to calculate each head's importance score, termed Taylor-expansion Importance Score (TIS), indicating its contribution to specific tasks. Additionally, three strategies for calculating TIS have been employed to maximize the effectiveness of TIS. These strategies calculate TIS from different perspectives, reflecting varying contributions of parameters. Besides ViT, HEAT has also been applied to hierarchical transformers such as Swin Transformer, demonstrating its versatility across different transformer architectures. Through extensive experiments, HEAT has demonstrated superior performance over state-of-the-art PETL methods on the VTAB-1K benchmark.

Side Information-Driven Session-based Recommendation: A Survey

The session-based recommendation (SBR) garners increasing attention due to its ability to predict anonymous user intents within limited interactions. Emerging efforts incorporate various kinds of side information into their methods for enhancing task performance. In this survey, we thoroughly review the side information-driven session-based recommendation from a data-centric perspective. Our survey commences with an illustration of the motivation and necessity behind this research topic. This is followed by a detailed exploration of various benchmarks rich in side information, pivotal for advancing research in this field. Moreover, we delve into how these diverse types of side information enhance SBR, underscoring their characteristics and utility. A systematic review of research progress is then presented, offering an analysis of the most recent and representative developments within this topic. Finally, we present the future prospects of this vibrant topic.